INDEX
    Explanations

    themes related to family and personal relationships

    New Auto-Interp
    Negative Logits
    лл
    -0.16
    ullan
    -0.15
    odi
    -0.15
    ucs
    -0.15
    anness
    -0.15
     Geg
    -0.14
    igan
    -0.14
     Atl
    -0.14
    ond
    -0.14
    ippi
    -0.14
    POSITIVE LOGITS
     home
    0.20
     HOME
    0.18
     loved
    0.18
     familiar
    0.17
    .home
    0.15
     loves
    0.15
     existing
    0.14
    HOME
    0.14
     hometown
    0.14
     love
    0.14
    Act Density 0.089%

    No Known Activations